A linear regression is a form of function-model (Chaps. 5, 8) between continuous variables. An output (dependent) variable y is approximated by a function f(x) of an input (independent) variable x with the error, y − f(x), being modelled by a model of continuous data (Chap. 4), most commonly by the Normal distribution (Sect. 4.3).
- 4.E. Anderson, The Irises of the Gaspe Peninsula. Bull. Am. Iris Soc. 59, 2–5 (1935)Google Scholar
- 30.R.A. Fisher, The use of multiple measurements in taxonomic problems. Ann. Eugenics 7(II), 179–188 (1936). https://doi.org/10.1111/j.1469-1809.1936.tb02137.x CrossRefGoogle Scholar
- 90.C.S. Wallace, Multiple factor analysis by MML estimation. Technical report 218, Department of Computer Science, Monash University, 1998. http://www.allisons.org/ll/Images/People/Wallace/Multi-Factor/
- 97.C.S. Wallace, P.R. Freeman, Single-factor analysis by minimum message length estimation. J. R. Stat. Soc. Ser. B Methodol. 195–209 (1992). http://www.jstor.org/stable/2345956